summaryrefslogtreecommitdiff
path: root/kernel/bpf
diff options
context:
space:
mode:
authorIlya Leoshkevich <iii@linux.ibm.com>2023-04-13 02:06:32 +0300
committerAlexei Starovoitov <ast@kernel.org>2023-04-14 07:36:41 +0300
commit1cf3bfc60f9836f44da951f58b6ae24680484b35 (patch)
tree21fb05b8e9d5df9fa212fd8517a88efbe98b9dd5 /kernel/bpf
parentc11bd046485d7bf1ca200db0e7d0bdc4bafdd395 (diff)
downloadlinux-1cf3bfc60f9836f44da951f58b6ae24680484b35.tar.xz
bpf: Support 64-bit pointers to kfuncs
test_ksyms_module fails to emit a kfunc call targeting a module on s390x, because the verifier stores the difference between kfunc address and __bpf_call_base in bpf_insn.imm, which is s32, and modules are roughly (1 << 42) bytes away from the kernel on s390x. Fix by keeping BTF id in bpf_insn.imm for BPF_PSEUDO_KFUNC_CALLs, and storing the absolute address in bpf_kfunc_desc. Introduce bpf_jit_supports_far_kfunc_call() in order to limit this new behavior to the s390x JIT. Otherwise other JITs need to be modified, which is not desired. Introduce bpf_get_kfunc_addr() instead of exposing both find_kfunc_desc() and struct bpf_kfunc_desc. In addition to sorting kfuncs by imm, also sort them by offset, in order to handle conflicting imms from different modules. Do this on all architectures in order to simplify code. Factor out resolving specialized kfuncs (XPD and dynptr) from fixup_kfunc_call(). This was required in the first place, because fixup_kfunc_call() uses find_kfunc_desc(), which returns a const pointer, so it's not possible to modify kfunc addr without stripping const, which is not nice. It also removes repetition of code like: if (bpf_jit_supports_far_kfunc_call()) desc->addr = func; else insn->imm = BPF_CALL_IMM(func); and separates kfunc_desc_tab fixups from kfunc_call fixups. Suggested-by: Jiri Olsa <olsajiri@gmail.com> Signed-off-by: Ilya Leoshkevich <iii@linux.ibm.com> Acked-by: Jiri Olsa <jolsa@kernel.org> Link: https://lore.kernel.org/r/20230412230632.885985-1-iii@linux.ibm.com Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Diffstat (limited to 'kernel/bpf')
-rw-r--r--kernel/bpf/core.c11
-rw-r--r--kernel/bpf/verifier.c123
2 files changed, 94 insertions, 40 deletions
diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index e2d256c82072..7421487422d4 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -1187,6 +1187,7 @@ int bpf_jit_get_func_addr(const struct bpf_prog *prog,
s16 off = insn->off;
s32 imm = insn->imm;
u8 *addr;
+ int err;
*func_addr_fixed = insn->src_reg != BPF_PSEUDO_CALL;
if (!*func_addr_fixed) {
@@ -1201,6 +1202,11 @@ int bpf_jit_get_func_addr(const struct bpf_prog *prog,
addr = (u8 *)prog->aux->func[off]->bpf_func;
else
return -EINVAL;
+ } else if (insn->src_reg == BPF_PSEUDO_KFUNC_CALL &&
+ bpf_jit_supports_far_kfunc_call()) {
+ err = bpf_get_kfunc_addr(prog, insn->imm, insn->off, &addr);
+ if (err)
+ return err;
} else {
/* Address of a BPF helper call. Since part of the core
* kernel, it's always at a fixed location. __bpf_call_base
@@ -2732,6 +2738,11 @@ bool __weak bpf_jit_supports_kfunc_call(void)
return false;
}
+bool __weak bpf_jit_supports_far_kfunc_call(void)
+{
+ return false;
+}
+
/* To execute LD_ABS/LD_IND instructions __bpf_prog_run() may call
* skb_copy_bits(), so provide a weak definition of it for NET-less config.
*/
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index e3d5a7a2f428..4aa6d715e655 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -195,6 +195,8 @@ static void invalidate_non_owning_refs(struct bpf_verifier_env *env);
static bool in_rbtree_lock_required_cb(struct bpf_verifier_env *env);
static int ref_set_non_owning(struct bpf_verifier_env *env,
struct bpf_reg_state *reg);
+static void specialize_kfunc(struct bpf_verifier_env *env,
+ u32 func_id, u16 offset, unsigned long *addr);
static bool bpf_map_ptr_poisoned(const struct bpf_insn_aux_data *aux)
{
@@ -2374,6 +2376,7 @@ struct bpf_kfunc_desc {
u32 func_id;
s32 imm;
u16 offset;
+ unsigned long addr;
};
struct bpf_kfunc_btf {
@@ -2383,6 +2386,11 @@ struct bpf_kfunc_btf {
};
struct bpf_kfunc_desc_tab {
+ /* Sorted by func_id (BTF ID) and offset (fd_array offset) during
+ * verification. JITs do lookups by bpf_insn, where func_id may not be
+ * available, therefore at the end of verification do_misc_fixups()
+ * sorts this by imm and offset.
+ */
struct bpf_kfunc_desc descs[MAX_KFUNC_DESCS];
u32 nr_descs;
};
@@ -2423,6 +2431,19 @@ find_kfunc_desc(const struct bpf_prog *prog, u32 func_id, u16 offset)
sizeof(tab->descs[0]), kfunc_desc_cmp_by_id_off);
}
+int bpf_get_kfunc_addr(const struct bpf_prog *prog, u32 func_id,
+ u16 btf_fd_idx, u8 **func_addr)
+{
+ const struct bpf_kfunc_desc *desc;
+
+ desc = find_kfunc_desc(prog, func_id, btf_fd_idx);
+ if (!desc)
+ return -EFAULT;
+
+ *func_addr = (u8 *)desc->addr;
+ return 0;
+}
+
static struct btf *__find_kfunc_desc_btf(struct bpf_verifier_env *env,
s16 offset)
{
@@ -2602,13 +2623,18 @@ static int add_kfunc_call(struct bpf_verifier_env *env, u32 func_id, s16 offset)
func_name);
return -EINVAL;
}
+ specialize_kfunc(env, func_id, offset, &addr);
- call_imm = BPF_CALL_IMM(addr);
- /* Check whether or not the relative offset overflows desc->imm */
- if ((unsigned long)(s32)call_imm != call_imm) {
- verbose(env, "address of kernel function %s is out of range\n",
- func_name);
- return -EINVAL;
+ if (bpf_jit_supports_far_kfunc_call()) {
+ call_imm = func_id;
+ } else {
+ call_imm = BPF_CALL_IMM(addr);
+ /* Check whether the relative offset overflows desc->imm */
+ if ((unsigned long)(s32)call_imm != call_imm) {
+ verbose(env, "address of kernel function %s is out of range\n",
+ func_name);
+ return -EINVAL;
+ }
}
if (bpf_dev_bound_kfunc_id(func_id)) {
@@ -2621,6 +2647,7 @@ static int add_kfunc_call(struct bpf_verifier_env *env, u32 func_id, s16 offset)
desc->func_id = func_id;
desc->imm = call_imm;
desc->offset = offset;
+ desc->addr = addr;
err = btf_distill_func_proto(&env->log, desc_btf,
func_proto, func_name,
&desc->func_model);
@@ -2630,19 +2657,19 @@ static int add_kfunc_call(struct bpf_verifier_env *env, u32 func_id, s16 offset)
return err;
}
-static int kfunc_desc_cmp_by_imm(const void *a, const void *b)
+static int kfunc_desc_cmp_by_imm_off(const void *a, const void *b)
{
const struct bpf_kfunc_desc *d0 = a;
const struct bpf_kfunc_desc *d1 = b;
- if (d0->imm > d1->imm)
- return 1;
- else if (d0->imm < d1->imm)
- return -1;
+ if (d0->imm != d1->imm)
+ return d0->imm < d1->imm ? -1 : 1;
+ if (d0->offset != d1->offset)
+ return d0->offset < d1->offset ? -1 : 1;
return 0;
}
-static void sort_kfunc_descs_by_imm(struct bpf_prog *prog)
+static void sort_kfunc_descs_by_imm_off(struct bpf_prog *prog)
{
struct bpf_kfunc_desc_tab *tab;
@@ -2651,7 +2678,7 @@ static void sort_kfunc_descs_by_imm(struct bpf_prog *prog)
return;
sort(tab->descs, tab->nr_descs, sizeof(tab->descs[0]),
- kfunc_desc_cmp_by_imm, NULL);
+ kfunc_desc_cmp_by_imm_off, NULL);
}
bool bpf_prog_has_kfunc_call(const struct bpf_prog *prog)
@@ -2665,13 +2692,14 @@ bpf_jit_find_kfunc_model(const struct bpf_prog *prog,
{
const struct bpf_kfunc_desc desc = {
.imm = insn->imm,
+ .offset = insn->off,
};
const struct bpf_kfunc_desc *res;
struct bpf_kfunc_desc_tab *tab;
tab = prog->aux->kfunc_tab;
res = bsearch(&desc, tab->descs, tab->nr_descs,
- sizeof(tab->descs[0]), kfunc_desc_cmp_by_imm);
+ sizeof(tab->descs[0]), kfunc_desc_cmp_by_imm_off);
return res ? &res->func_model : NULL;
}
@@ -17293,11 +17321,45 @@ static int fixup_call_args(struct bpf_verifier_env *env)
return err;
}
+/* replace a generic kfunc with a specialized version if necessary */
+static void specialize_kfunc(struct bpf_verifier_env *env,
+ u32 func_id, u16 offset, unsigned long *addr)
+{
+ struct bpf_prog *prog = env->prog;
+ bool seen_direct_write;
+ void *xdp_kfunc;
+ bool is_rdonly;
+
+ if (bpf_dev_bound_kfunc_id(func_id)) {
+ xdp_kfunc = bpf_dev_bound_resolve_kfunc(prog, func_id);
+ if (xdp_kfunc) {
+ *addr = (unsigned long)xdp_kfunc;
+ return;
+ }
+ /* fallback to default kfunc when not supported by netdev */
+ }
+
+ if (offset)
+ return;
+
+ if (func_id == special_kfunc_list[KF_bpf_dynptr_from_skb]) {
+ seen_direct_write = env->seen_direct_write;
+ is_rdonly = !may_access_direct_pkt_data(env, NULL, BPF_WRITE);
+
+ if (is_rdonly)
+ *addr = (unsigned long)bpf_dynptr_from_skb_rdonly;
+
+ /* restore env->seen_direct_write to its original value, since
+ * may_access_direct_pkt_data mutates it
+ */
+ env->seen_direct_write = seen_direct_write;
+ }
+}
+
static int fixup_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn,
struct bpf_insn *insn_buf, int insn_idx, int *cnt)
{
const struct bpf_kfunc_desc *desc;
- void *xdp_kfunc;
if (!insn->imm) {
verbose(env, "invalid kernel function call not eliminated in verifier pass\n");
@@ -17306,18 +17368,9 @@ static int fixup_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn,
*cnt = 0;
- if (bpf_dev_bound_kfunc_id(insn->imm)) {
- xdp_kfunc = bpf_dev_bound_resolve_kfunc(env->prog, insn->imm);
- if (xdp_kfunc) {
- insn->imm = BPF_CALL_IMM(xdp_kfunc);
- return 0;
- }
-
- /* fallback to default kfunc when not supported by netdev */
- }
-
- /* insn->imm has the btf func_id. Replace it with
- * an address (relative to __bpf_call_base).
+ /* insn->imm has the btf func_id. Replace it with an offset relative to
+ * __bpf_call_base, unless the JIT needs to call functions that are
+ * further than 32 bits away (bpf_jit_supports_far_kfunc_call()).
*/
desc = find_kfunc_desc(env->prog, insn->imm, insn->off);
if (!desc) {
@@ -17326,7 +17379,8 @@ static int fixup_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn,
return -EFAULT;
}
- insn->imm = desc->imm;
+ if (!bpf_jit_supports_far_kfunc_call())
+ insn->imm = BPF_CALL_IMM(desc->addr);
if (insn->off)
return 0;
if (desc->func_id == special_kfunc_list[KF_bpf_obj_new_impl]) {
@@ -17351,17 +17405,6 @@ static int fixup_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn,
desc->func_id == special_kfunc_list[KF_bpf_rdonly_cast]) {
insn_buf[0] = BPF_MOV64_REG(BPF_REG_0, BPF_REG_1);
*cnt = 1;
- } else if (desc->func_id == special_kfunc_list[KF_bpf_dynptr_from_skb]) {
- bool seen_direct_write = env->seen_direct_write;
- bool is_rdonly = !may_access_direct_pkt_data(env, NULL, BPF_WRITE);
-
- if (is_rdonly)
- insn->imm = BPF_CALL_IMM(bpf_dynptr_from_skb_rdonly);
-
- /* restore env->seen_direct_write to its original value, since
- * may_access_direct_pkt_data mutates it
- */
- env->seen_direct_write = seen_direct_write;
}
return 0;
}
@@ -17891,7 +17934,7 @@ patch_call_imm:
}
}
- sort_kfunc_descs_by_imm(env->prog);
+ sort_kfunc_descs_by_imm_off(env->prog);
return 0;
}